https://ir.ymlib.yonsei.ac.kr/handle/22282913/174501 2026-04-20T08:49:00Z 2026-04-20T08:49:00Z Ahn, Sang Hyun Kim, Junhewk https://ir.ymlib.yonsei.ac.kr/handle/22282913/211733 2026-04-03T00:32:20Z 2026-03-01T00:00:00Z

Title: Strategic Governance of Artificial Intelligence-Enabled Clinical Algorithm Development: Formative Evaluation of the Semiautomatic Clinical Algorithm Development Framework Authors: Ahn, Sang Hyun; Kim, Junhewk Abstract: Background: Health care leaders face a strategic dilemma: traditional expert-led content development ensures safety but is too slow for digital innovation, whereas artificial intelligence (AI) automation offers speed but introduces risks from hallucinations. Resolving this tension requires governance frameworks that balance operational efficiency with rigorous accountability for patient safety. Objective: This study describes the development process and conducts a formative evaluation of the Semiautomatic Clinical Algorithm Development (S-ACAD) framework as an industry-driven implementation strategy. We aimed to assess the feasibility of this "human-in-the-loop" governance model in balancing the need for operational efficiency with the rigorous safety standards required for pediatric emergency guidance. Methods: We conducted a prospective, single-day proof-of-concept case study focusing on pediatric febrile seizures. A single (3) iterative refinement via "AI sparring," and (4) final clinical validation. The resulting algorithm was reviewed by 2 independent external pediatric specialists. We benchmarked this process against a fully automated system (Fully Autonomous Clinical Algorithm Development [F-ACAD]) to illustrate comparative efficiency and safety trade-offs. Results: In this single execution, the S-ACAD framework produced a parent-actionable febrile seizure algorithm in approximately 245 minutes. Two independent pediatric specialists (N=2) reviewed the output and did not identify medically inaccurate sections or critical safety errors requiring mandatory correction, and both rated overall clinical validity highly (9.0 and 9.5 out of 10). During the workflow, 19 human expert interventions were recorded, with clinical judgment (n=8, 42.1%) and safety review (n=5, 26.3%) as the most frequent categories in an exploratory post hoc analysis. By comparison, the fully automated approach (F-ACAD) completed the task in approximately 68 minutes, but its own AI critics identified 17 issues (9 high-priority), including concerns related to emergency response clarity and standard-of-care alignment. Conclusions: These preliminary findings suggest that the S-ACAD framework may offer a potential pathway for "active governance" in AI-assisted clinical content development. In this proof-of-concept case, the framework combined rapid AI-assisted drafting with continuous expert oversight and independent clinical review, suggesting the potential to reduce turnaround time topic, and validation across multiple experts, topics, and institutional contexts is needed before generalizability can be established.

2026-03-01T00:00:00Z Kim, Min Ji Yoo, Sang-Ho Woo, Kyung-Sook Choi, Heeseung Chang, Eunsuk Choi, Kyungsuk Park, Young Su Kim, Yoongu Kim, Do Hoon Kim, Junhewk Shin, Dong Wook https://ir.ymlib.yonsei.ac.kr/handle/22282913/211099 2026-03-11T00:17:29Z 2026-01-01T00:00:00Z

Title: Toward the Implementation of Shared Decision-Making in Korean Clinical Practice: Study Protocol for a Foundational Research Project Authors: Kim, Min Ji; Yoo, Sang-Ho; Woo, Kyung-Sook; Choi, Heeseung; Chang, Eunsuk; Choi, Kyungsuk; Park, Young Su; Kim, Yoongu; Kim, Do Hoon; Kim, Junhewk; Shin, Dong Wook Abstract: Shared decision-making (SDM) is an essential component of patient-centered care, yet its implementation in South Korea remains limited due to a persistent physician-centered clinical culture. This project, supported by the Ministry of Health and Welfare, aims to establish a foundation for nationwide SDM implementation by developing a culturally adapted Korean SDM model and creating a framework to support its institutionalization and widespread clinical adoption. This four-year project consists of five interlinked work packages (WPs) organized into two phases, each lasting two years. Using a multi-method approach-comprising nationwide surveys, systematic literature reviews, and psychometric validation studies-we will assess the current landscape (WP1) and develop standardized SDM evaluation tools for primary stakeholders (WP2). A clinical research data management system will be designed and implemented to support data integration and monitoring (WP3). The central component involves developing a Korean SDM conceptual model and corresponding implementation strategies (WP4). Economic evaluations and legal analyses will inform the design of a pilot reimbursement framework to support sustainable system-level integration (WP5). The project is expected to produce the following outcomes: i) an analysis of domestic and international SDM trends; ii) validated SDM assessment tools and guidelines tailored for the Korean context; iii) a standardized and interoperable SDM data management system; iv) a culturally grounded Korean SDM model with evidence-based implementation strategies; and v) policy proposals, including a reimbursement model, to facilitate system-wide adoption. This work will provide the theoretical, empirical, and policy basis required to advance SDM within the Korean healthcare system. By addressing cultural characteristics and structural barriers, the resulting SDM model and policy recommendations are expected to support the sustainable institutionalization of SDM and strengthen patient autonomy and the quality of clinical practice in Korea.

2026-01-01T00:00:00Z Kim, Jaeyeon Huh, Jisun Park, Geun U. Kim, Jun-young Park, Wonse https://ir.ymlib.yonsei.ac.kr/handle/22282913/210245 2026-01-23T05:37:22Z 2025-12-01T00:00:00Z

Title: Systemic Conditions and Medication Use in Older Patients Undergoing Dental Implants: A Nationwide Cross-Sectional Study Authors: Kim, Jaeyeon; Huh, Jisun; Park, Geun U.; Kim, Jun-young; Park, Wonse Abstract: Introduction: Dental implants are widely utilized to manage both partially and completely edentulous older patients. However, such patients often present with multiple systemic diseases and may be at an increased risk of complications before and after implant surgery. Nevertheless, population-level data on systemic diseases and medication use in these patients remain limited. Methods: This retrospective, cross-sectional study analyzed 36 957 patients who underwent 43 171 insurance-covered implant surgeries between 2014 and 2019 using the National Health Insurance Service-National Sample Cohort (NHIS-NSC) database. Patients aged 65 years or older were included. Sociodemographic characteristics, diagnosis of systemic diseases within 1 year before implant surgery, medication history, and type of medical institution were evaluated. Additionally, logistic regression analysis was performed to investigate factors associated with implant removal. Results: Among 36 957 patients who underwent 43 171 implant surgeries, implant removal occurred in 803 patients. Within 1 year before surgery, 89.33% had at least one systemic disease, including hypertension (57.92%), arthritis (43.39%), and diabetes (34.62%). Antithrombotic and antiresorptive agents were prescribed to 6.77% and 5.05% of patients, respectively. The use of intravenous (IV) bisphosphonates, denosumab, and direct oral anticoagulants (DOACs) increased, whereas the use of oral bisphosphonates and warfarin decreased. Logistic regression analysis showed that cerebrovascular and kidney disease increased the risk of implant removal, whereas osteoporosis and antiresorptive agents decreased the risk. Conclusion: Most older patients who underwent implant surgery had systemic diseases, and approximately 10% were prescribed medications. Cerebrovascular and kidney diseases increased the risk of implant removal, whereas osteoporosis or antiresorptive therapy decreased the risk. With the increasing use of DOACs, IV bisphosphonates, and denosumab, clinicians carefully review the medical histories of older implant patients.

2025-12-01T00:00:00Z Cha, Hyunjae Kim, Junhewk https://ir.ymlib.yonsei.ac.kr/handle/22282913/210256 2026-01-23T07:49:18Z 2025-12-01T00:00:00Z

Title: Ethical considerations of artificial intelligence in emergency medicine for triage and resource allocation: a scoping review Authors: Cha, Hyunjae; Kim, Junhewk Abstract: Objective This study aims to systematically review the ethical and legal discussions regarding the utilization of artificial intelligence (AI) for patient triage and resource allocation in emergency medicine, and to identify the current state of discussions, their limitations, and future research directions. Methods A comprehensive literature search was conducted following scoping review methodology. Relevant literature published after January 2020 was searched in the Web of Science, Scopus, CINAHL, PubMed, and Cochrane Library databases. Based on a PCC (population, concept, and context) framework (emergency patients/medical staff; triage, resource allocation; and emergency medicine with AI application), a final selection of 27 articles was analyzed. Results The selected literature raised various ethical and legal issues related to the introduction of AI triage systems and AI utilization in emergency medicine, including data privacy, algorithmic bias, automation dependency, accountability, and explainability. In response to these issues, human-centered design, implementation of explainable AI, establishment of regulatory frameworks, continuous verification and evaluation, and ensuring human-in-the-loop were discussed as major solutions. However, discussions on the risks of "persuasive AI" that could mislead users, ethical issues of generative AI, and social validation and patient and public involvement were found to be insufficient. Conclusion Ethical and legal discussions regarding AI in emergency medicine are evolving toward seeking concrete solutions at technical, institutional, and relational dimensions. However, in-depth research on ethical challenges, such as reflecting the specificity of rapidly developing AI and the values of emergency medicine, is urgently required.

2025-12-01T00:00:00Z